{"id":"https://openalex.org/W2923328826","doi":"https://doi.org/10.1177/1094342020945005","title":"A study of vectorization for matrix-free finite element methods","display_name":"A study of vectorization for matrix-free finite element methods","publication_year":2020,"publication_date":"2020-07-31","ids":{"openalex":"https://openalex.org/W2923328826","doi":"https://doi.org/10.1177/1094342020945005","mag":"2923328826"},"language":"en","primary_location":{"id":"doi:10.1177/1094342020945005","is_oa":true,"landing_page_url":"https://doi.org/10.1177/1094342020945005","pdf_url":null,"source":{"id":"https://openalex.org/S60606485","display_name":"The International Journal of High Performance Computing Applications","issn_l":"1094-3420","issn":["1094-3420","1741-2846"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320017","host_organization_name":"SAGE Publishing","host_organization_lineage":["https://openalex.org/P4310320017"],"host_organization_lineage_names":["SAGE Publishing"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The International Journal of High Performance Computing Applications","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1177/1094342020945005","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Tianjiao Sun","orcid":"https://orcid.org/0000-0003-4223-6700"},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Tianjiao Sun","raw_affiliation_strings":["Department of Computer Science, Imperial College, London, UK"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Imperial College, London, UK","institution_ids":["https://openalex.org/I47508984"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Lawrence Mitchell","orcid":null},"institutions":[{"id":"https://openalex.org/I190082696","display_name":"Durham University","ror":"https://ror.org/01v29qb04","country_code":"GB","type":"education","lineage":["https://openalex.org/I190082696"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Lawrence Mitchell","raw_affiliation_strings":["Department of Computer Science, Durham University, Durham, UK"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Durham University, Durham, UK","institution_ids":["https://openalex.org/I190082696"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Kaushik Kulkarni","orcid":null},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kaushik Kulkarni","raw_affiliation_strings":["Department of Computer Science, University of Illinois at Urbana-Champaign, IL, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Illinois at Urbana-Champaign, IL, USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Andreas Kl\u00f6ckner","orcid":null},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Andreas Kl\u00f6ckner","raw_affiliation_strings":["Department of Computer Science, University of Illinois at Urbana-Champaign, IL, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Illinois at Urbana-Champaign, IL, USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":null,"display_name":"David A Ham","orcid":null},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"David A Ham","raw_affiliation_strings":["Department of Mathematics, Imperial College, London, UK"],"affiliations":[{"raw_affiliation_string":"Department of Mathematics, Imperial College, London, UK","institution_ids":["https://openalex.org/I47508984"]}]},{"author_position":"last","author":{"id":null,"display_name":"Paul HJ Kelly","orcid":"https://orcid.org/0000-0001-5905-1804"},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Paul HJ Kelly","raw_affiliation_strings":["Department of Computer Science, Imperial College, London, UK"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Imperial College, London, UK","institution_ids":["https://openalex.org/I47508984"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I47508984"],"apc_list":null,"apc_paid":null,"fwci":2.593,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":{"value":0.89313408,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":"34","issue":"6","first_page":"629","last_page":"644"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.7192000150680542,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.7192000150680542,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10339","display_name":"Advanced Numerical Methods in Computational Mathematics","score":0.11569999903440475,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10792","display_name":"Matrix Theory and Algorithms","score":0.08799999952316284,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/vectorization","display_name":"Vectorization (mathematics)","score":0.8707000017166138},{"id":"https://openalex.org/keywords/finite-element-method","display_name":"Finite element method","score":0.6281999945640564},{"id":"https://openalex.org/keywords/simd","display_name":"SIMD","score":0.593999981880188},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.5408999919891357},{"id":"https://openalex.org/keywords/interface","display_name":"Interface (matter)","score":0.5224000215530396},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.47110000252723694},{"id":"https://openalex.org/keywords/transformation","display_name":"Transformation (genetics)","score":0.44760000705718994},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.4113999903202057}],"concepts":[{"id":"https://openalex.org/C41681595","wikidata":"https://www.wikidata.org/wiki/Q7917855","display_name":"Vectorization (mathematics)","level":2,"score":0.8707000017166138},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6542999744415283},{"id":"https://openalex.org/C135628077","wikidata":"https://www.wikidata.org/wiki/Q220184","display_name":"Finite element method","level":2,"score":0.6281999945640564},{"id":"https://openalex.org/C150552126","wikidata":"https://www.wikidata.org/wiki/Q339387","display_name":"SIMD","level":2,"score":0.593999981880188},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.5408999919891357},{"id":"https://openalex.org/C113843644","wikidata":"https://www.wikidata.org/wiki/Q901882","display_name":"Interface (matter)","level":4,"score":0.5224000215530396},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.47110000252723694},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.460999995470047},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4593999981880188},{"id":"https://openalex.org/C204241405","wikidata":"https://www.wikidata.org/wiki/Q461499","display_name":"Transformation (genetics)","level":3,"score":0.44760000705718994},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.4113999903202057},{"id":"https://openalex.org/C90119067","wikidata":"https://www.wikidata.org/wiki/Q43260","display_name":"Polynomial","level":2,"score":0.3901999890804291},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.37540000677108765},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.37220001220703125},{"id":"https://openalex.org/C124304363","wikidata":"https://www.wikidata.org/wiki/Q673661","display_name":"Abstraction","level":2,"score":0.3612000048160553},{"id":"https://openalex.org/C200288055","wikidata":"https://www.wikidata.org/wiki/Q2621792","display_name":"Element (criminal law)","level":2,"score":0.35109999775886536},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3183000087738037},{"id":"https://openalex.org/C88482812","wikidata":"https://www.wikidata.org/wiki/Q6453666","display_name":"Modular programming","level":2,"score":0.3075999915599823},{"id":"https://openalex.org/C55439883","wikidata":"https://www.wikidata.org/wiki/Q360812","display_name":"Correctness","level":2,"score":0.3057999908924103},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.2842999994754791},{"id":"https://openalex.org/C55526617","wikidata":"https://www.wikidata.org/wiki/Q719375","display_name":"Operand","level":2,"score":0.27799999713897705},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.2694999873638153},{"id":"https://openalex.org/C154690210","wikidata":"https://www.wikidata.org/wiki/Q1668499","display_name":"Rewriting","level":2,"score":0.2630000114440918},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.2612000107765198},{"id":"https://openalex.org/C73000952","wikidata":"https://www.wikidata.org/wiki/Q17007827","display_name":"Discretization","level":2,"score":0.26080000400543213}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1177/1094342020945005","is_oa":true,"landing_page_url":"https://doi.org/10.1177/1094342020945005","pdf_url":null,"source":{"id":"https://openalex.org/S60606485","display_name":"The International Journal of High Performance Computing Applications","issn_l":"1094-3420","issn":["1094-3420","1741-2846"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320017","host_organization_name":"SAGE Publishing","host_organization_lineage":["https://openalex.org/P4310320017"],"host_organization_lineage_names":["SAGE Publishing"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The International Journal of High Performance Computing Applications","raw_type":"journal-article"},{"id":"pmh:oai:dro.dur.ac.uk.OAI2:31191","is_oa":true,"landing_page_url":"http://dro.dur.ac.uk/31191/","pdf_url":null,"source":{"id":"https://openalex.org/S4377196258","display_name":"Durham Research Online (Durham University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I190082696","host_organization_name":"Durham University","host_organization_lineage":["https://openalex.org/I190082696"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"International journal of high performance computing applications, 2020, Vol.34(6), pp.629-644 [Peer Reviewed Journal]","raw_type":"Article"},{"id":"pmh:oai:arXiv.org:1903.08243","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1903.08243","pdf_url":"https://arxiv.org/pdf/1903.08243","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:durham-repository.worktribe.com:1303781","is_oa":true,"landing_page_url":"https://durham-repository.worktribe.com/output/1303781","pdf_url":null,"source":{"id":"https://openalex.org/S4306400188","display_name":"Durham Research Online (Durham University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I190082696","host_organization_name":"Durham University","host_organization_lineage":["https://openalex.org/I190082696"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"publishedVersion"},{"id":"pmh:oai:spiral.imperial.ac.uk:10044/1/90136","is_oa":true,"landing_page_url":"http://hdl.handle.net/10044/1/90136","pdf_url":null,"source":{"id":"https://openalex.org/S4306401396","display_name":"Spiral (Imperial College London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I47508984","host_organization_name":"Imperial College London","host_organization_lineage":["https://openalex.org/I47508984"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"644","raw_type":"Journal Article"}],"best_oa_location":{"id":"doi:10.1177/1094342020945005","is_oa":true,"landing_page_url":"https://doi.org/10.1177/1094342020945005","pdf_url":null,"source":{"id":"https://openalex.org/S60606485","display_name":"The International Journal of High Performance Computing Applications","issn_l":"1094-3420","issn":["1094-3420","1741-2846"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320017","host_organization_name":"SAGE Publishing","host_organization_lineage":["https://openalex.org/P4310320017"],"host_organization_lineage_names":["SAGE Publishing"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The International Journal of High Performance Computing Applications","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1934935867","display_name":null,"funder_award_id":"Engineering and Physical Sciences R","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G2249403966","display_name":null,"funder_award_id":"EP/I00677X/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G3957501995","display_name":null,"funder_award_id":"EP/R029423/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G4162891482","display_name":null,"funder_award_id":"R029423/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G5201431165","display_name":"EPSRC Centre for Doctoral Training in High Performance Embedded and Distributed Systems","funder_award_id":"EP/L016796/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G6653872853","display_name":null,"funder_award_id":"EP/L016","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G7215042158","display_name":null,"funder_award_id":"NE/K008951/1","funder_id":"https://openalex.org/F4320334631","funder_display_name":"Natural Environment Research Council"},{"id":"https://openalex.org/G7295259756","display_name":"PRISM: Platform for Research In Simulation Methods","funder_award_id":"EP/R029423/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G731814487","display_name":null,"funder_award_id":"EP/I006761/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G7554227835","display_name":null,"funder_award_id":"EP/L000407/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G8057849231","display_name":null,"funder_award_id":"NE/K008951/1","funder_id":"https://openalex.org/F4320320022","funder_display_name":"Sight Research UK"}],"funders":[{"id":"https://openalex.org/F4320320022","display_name":"Sight Research UK","ror":"https://ror.org/03z2py885"},{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"},{"id":"https://openalex.org/F4320334631","display_name":"Natural Environment Research Council","ror":"https://ror.org/02b5d8509"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W1558370006","https://openalex.org/W1965742121","https://openalex.org/W2002555321","https://openalex.org/W2008060144","https://openalex.org/W2038646072","https://openalex.org/W2082187902","https://openalex.org/W2107979247","https://openalex.org/W2168522485","https://openalex.org/W2228844421","https://openalex.org/W2342281373","https://openalex.org/W2612795562","https://openalex.org/W2622013296","https://openalex.org/W4244104762","https://openalex.org/W4245654886","https://openalex.org/W6893421957","https://openalex.org/W6907623716","https://openalex.org/W6912078545"],"related_works":[],"abstract_inverted_index":{"Vectorization":[0],"is":[1,25,62],"increasingly":[2],"important":[3],"to":[4,38,154],"achieve":[5,126],"high":[6,144],"performance":[7,131],"on":[8,109],"modern":[9],"hardware":[10],"with":[11,46,143,147],"SIMD":[12],"instructions.":[13],"Assembly":[14],"of":[15,50,91,100,128,135],"matrices":[16],"and":[17,69,87,107,138],"vectors":[18],"in":[19,78],"the":[20,58,79,89,155],"finite":[21,59,80],"element":[22,60,81],"method,":[23],"which":[24],"characterized":[26],"by":[27,95],"iterating":[28],"a":[29,42,47,63,97],"local":[30,156],"assembly":[31,157],"kernel":[32],"over":[33,150],"unstructured":[34],"meshes,":[35],"poses":[36],"difficulties":[37],"effective":[39],"vectorization.":[40],"Maintaining":[41],"user-friendly":[43],"high-level":[44],"interface":[45],"suitable":[48],"degree":[49],"abstraction":[51],"while":[52],"generating":[53],"efficient,":[54],"vectorized":[55],"code":[56,85],"for":[57,65,123,132,141],"method":[61],"challenge":[64],"numerical":[66],"software":[67],"systems":[68],"libraries.":[70],"In":[71],"this":[72],"work,":[73],"we":[74],"study":[75],"cross-element":[76,124],"vectorization":[77,125,152],"framework":[82],"Firedrake":[83],"via":[84],"transformation":[86],"demonstrate":[88],"efficacy":[90],"such":[92],"an":[93],"approach":[94],"evaluating":[96],"wide":[98],"range":[99],"matrix-free":[101],"operators":[102],"spanning":[103],"different":[104],"polynomial":[105],"degrees":[106],"discretizations":[108],"two":[110],"recent":[111],"CPUs":[112],"using":[113],"three":[114],"mainstream":[115],"compilers.":[116],"Our":[117],"experiments":[118],"show":[119],"that":[120],"our":[121],"approaches":[122],"30%":[127],"theoretical":[129],"peak":[130],"many":[133],"examples":[134],"practical":[136],"significance,":[137],"exceed":[139],"50%":[140],"cases":[142],"arithmetic":[145],"intensities,":[146],"consistent":[148],"speed-up":[149],"(intra-element)":[151],"restricted":[153],"kernels.":[158]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":5}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2019-04-01T00:00:00"}
